Claims › Agent model › C006
C006
In their own words · Andreas 2022 · §1 Introduction, (C1) · contested
…In particular, I claim:
“In the course of performing next-word prediction in context, current LMs sometimes infer approximate, partial representations of the beliefs, desires and intentions possessed by the agent that produced the context, and other agents mentioned within it.”
(C2) Once these representations are inferred, they are causally linked to LM prediction, and thus bear the same relation to generated text that an intentional agent’s state bears to its communciative actions.…
Predicting the next word can require the model to build a partial picture of what the writer believed and wanted. The claim is about representations inside the system, not about the system being someone.
The five layers, for this claim
The same core in the infographic, with the claims it touches.
Relations
- contests → C008 A system trained only on the shape of language has nothing in its input that could tell it what the language is about. If the model infers representations of intentions, form alone does not stay mute, as Bender and Koller claim it must.
- ← refines C010 The premise the whole framework rests on, in its narrow form: a model may represent that a passage is in Spanish, or that it is being evaluated, without representing that the assertion it is about to make is causal rather than correlational. A model may represent what the writer wanted without representing what kind of claim it is about to make.
Notation
- Claim typeWhat kind of statement it is, so that the right test can be applied. Proposed until checked by hand.
- D1.14 · metaphysical-ontological
- FunctionWhat a claim does for the programme: a conceptual tool, a working method, corrective evidence, a technical reference.
- conceptual tool
- StanceHow the programme holds the claim: assumed, used, or contested.
- contested
- Used in
- /lab/2026-07-21-what-counts-as-a-verdict/
- Cite this
- claudiocammarano.com/en/claims/c006/